Downloads · 30 days
23
48% of all-time downloads
bert_tiny_lda_50_v1_book_stsb
gokulsrinivasagan/bert_tiny_lda_50_v1_book_stsb
bert_tiny_lda_50_v1_book_stsb is a text classification model from gokulsrinivasagan. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
48
Public
Parameters
33M
396 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors132 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Dec 10, 2024
- Updated
- Dec 10, 2024
- SHA
- 0f715b87
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bert_tiny_lda_50_v1_book_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_50_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.7765
- Pearson: 0.8096
- Spearmanr: 0.8063
- Combined Score: 0.8079
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 3.1328 | 1.0 | 23 | 2.3622 | 0.1604 | 0.1560 | 0.1582 |
| 1.6491 | 2.0 | 46 | 1.2493 | 0.6936 | 0.6923 | 0.6929 |
| 1.0764 | 3.0 | 69 | 0.9237 | 0.7806 | 0.7829 | 0.7817 |
| 0.841 | 4.0 | 92 | 0.8324 | 0.7964 | 0.7931 | 0.7947 |
| 0.7096 | 5.0 | 115 | 0.8547 | 0.8016 | 0.7997 | 0.8007 |
| 0.6168 | 6.0 | 138 | 0.7765 | 0.8096 | 0.8063 | 0.8079 |
| 0.5783 | 7.0 | 161 | 0.8441 | 0.8112 | 0.8103 | 0.8108 |
| 0.4968 | 8.0 | 184 | 0.7933 | 0.8098 | 0.8071 | 0.8085 |
| 0.4336 | 9.0 | 207 | 0.7825 | 0.8083 | 0.8056 | 0.8069 |
| 0.3838 | 10.0 | 230 | 0.8449 | 0.8119 | 0.8104 | 0.8111 |
| 0.3402 | 11.0 | 253 | 0.7965 | 0.8090 | 0.8072 | 0.8081 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en
- Created
- Dec 10, 2024
- Updated
- Dec 10, 2024